Brain MR radiomics to differentiate cognitive disorders

Alzheimer’s Disease Neuroimaging Initiative

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Objective: Subtle and gradual changes occur in the brain years before cognitive impairment due to age-related neurodegenerative disorders. The authors examined the utility of hippocampal texture analysis and volumetric features extracted from brain magnetic resonance (MR) data to differentiate between three cognitive groups (cognitively normal individuals, individuals with mild cognitive impairment, and individuals with Alzheimer’s disease) and neuropsychological scores on the Clinical Dementia Rating (CDR) scale. Methods: Data from 173 uni que pati ents with 3-T T1-weighted MR images from the Alzheimer’s Disease Neuroimaging Initiative database were analyzed. A variety of texture and volumetric features were extracted from bilateral hippocampal regions and were used to perform binary classification of cognitive groups and CDR scores. The authors used diagonal quadratic discriminant analysis in a leave-one-out cross-validation scheme. Sensitivity, specificity, and area under the receiver operating characteristic curve were used to assess the performance of models. Results: The results show promise for hippocampal texture analysis to distinguish between no impairment and early stages of impairment. Volumetric features were more successful at differentiating between no impairment and advanced stages of impairment. Conclusions: MR radiomics may be a promising tool to classify various cognitive groups.

Original languageEnglish (US)
Pages (from-to)210-219
Number of pages10
JournalJournal of Neuropsychiatry and Clinical Neurosciences
Volume31
Issue number3
DOIs
StatePublished - Jul 1 2019

Fingerprint

Magnetic Resonance Spectroscopy
Dementia
Alzheimer Disease
Brain
Discriminant Analysis
Neuroimaging
ROC Curve
Neurodegenerative Diseases
Databases
Sensitivity and Specificity
Cognitive Dysfunction
3-monoiodothyronine

ASJC Scopus subject areas

  • Clinical Neurology
  • Psychiatry and Mental health

Cite this

Brain MR radiomics to differentiate cognitive disorders. / Alzheimer’s Disease Neuroimaging Initiative.

In: Journal of Neuropsychiatry and Clinical Neurosciences, Vol. 31, No. 3, 01.07.2019, p. 210-219.

Research output: Contribution to journalArticle

Alzheimer’s Disease Neuroimaging Initiative. / Brain MR radiomics to differentiate cognitive disorders. In: Journal of Neuropsychiatry and Clinical Neurosciences. 2019 ; Vol. 31, No. 3. pp. 210-219.
@article{072d71383d104cbf972beb364628b466,
title = "Brain MR radiomics to differentiate cognitive disorders",
abstract = "Objective: Subtle and gradual changes occur in the brain years before cognitive impairment due to age-related neurodegenerative disorders. The authors examined the utility of hippocampal texture analysis and volumetric features extracted from brain magnetic resonance (MR) data to differentiate between three cognitive groups (cognitively normal individuals, individuals with mild cognitive impairment, and individuals with Alzheimer’s disease) and neuropsychological scores on the Clinical Dementia Rating (CDR) scale. Methods: Data from 173 uni que pati ents with 3-T T1-weighted MR images from the Alzheimer’s Disease Neuroimaging Initiative database were analyzed. A variety of texture and volumetric features were extracted from bilateral hippocampal regions and were used to perform binary classification of cognitive groups and CDR scores. The authors used diagonal quadratic discriminant analysis in a leave-one-out cross-validation scheme. Sensitivity, specificity, and area under the receiver operating characteristic curve were used to assess the performance of models. Results: The results show promise for hippocampal texture analysis to distinguish between no impairment and early stages of impairment. Volumetric features were more successful at differentiating between no impairment and advanced stages of impairment. Conclusions: MR radiomics may be a promising tool to classify various cognitive groups.",
author = "{Alzheimer’s Disease Neuroimaging Initiative} and Sara Ranjbar and Velgos, {Stefanie N.} and Amylou Dueck and Geda, {Yonas Endale} and Mitchell, {J. Ross}",
year = "2019",
month = "7",
day = "1",
doi = "10.1176/appi.neuropsych.17120366",
language = "English (US)",
volume = "31",
pages = "210--219",
journal = "Journal of Neuropsychiatry and Clinical Neurosciences",
issn = "0895-0172",
publisher = "American Psychiatric Publishing Inc.",
number = "3",

}

TY - JOUR

T1 - Brain MR radiomics to differentiate cognitive disorders

AU - Alzheimer’s Disease Neuroimaging Initiative

AU - Ranjbar, Sara

AU - Velgos, Stefanie N.

AU - Dueck, Amylou

AU - Geda, Yonas Endale

AU - Mitchell, J. Ross

PY - 2019/7/1

Y1 - 2019/7/1

N2 - Objective: Subtle and gradual changes occur in the brain years before cognitive impairment due to age-related neurodegenerative disorders. The authors examined the utility of hippocampal texture analysis and volumetric features extracted from brain magnetic resonance (MR) data to differentiate between three cognitive groups (cognitively normal individuals, individuals with mild cognitive impairment, and individuals with Alzheimer’s disease) and neuropsychological scores on the Clinical Dementia Rating (CDR) scale. Methods: Data from 173 uni que pati ents with 3-T T1-weighted MR images from the Alzheimer’s Disease Neuroimaging Initiative database were analyzed. A variety of texture and volumetric features were extracted from bilateral hippocampal regions and were used to perform binary classification of cognitive groups and CDR scores. The authors used diagonal quadratic discriminant analysis in a leave-one-out cross-validation scheme. Sensitivity, specificity, and area under the receiver operating characteristic curve were used to assess the performance of models. Results: The results show promise for hippocampal texture analysis to distinguish between no impairment and early stages of impairment. Volumetric features were more successful at differentiating between no impairment and advanced stages of impairment. Conclusions: MR radiomics may be a promising tool to classify various cognitive groups.

AB - Objective: Subtle and gradual changes occur in the brain years before cognitive impairment due to age-related neurodegenerative disorders. The authors examined the utility of hippocampal texture analysis and volumetric features extracted from brain magnetic resonance (MR) data to differentiate between three cognitive groups (cognitively normal individuals, individuals with mild cognitive impairment, and individuals with Alzheimer’s disease) and neuropsychological scores on the Clinical Dementia Rating (CDR) scale. Methods: Data from 173 uni que pati ents with 3-T T1-weighted MR images from the Alzheimer’s Disease Neuroimaging Initiative database were analyzed. A variety of texture and volumetric features were extracted from bilateral hippocampal regions and were used to perform binary classification of cognitive groups and CDR scores. The authors used diagonal quadratic discriminant analysis in a leave-one-out cross-validation scheme. Sensitivity, specificity, and area under the receiver operating characteristic curve were used to assess the performance of models. Results: The results show promise for hippocampal texture analysis to distinguish between no impairment and early stages of impairment. Volumetric features were more successful at differentiating between no impairment and advanced stages of impairment. Conclusions: MR radiomics may be a promising tool to classify various cognitive groups.

UR - http://www.scopus.com/inward/record.url?scp=85070062632&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070062632&partnerID=8YFLogxK

U2 - 10.1176/appi.neuropsych.17120366

DO - 10.1176/appi.neuropsych.17120366

M3 - Article

VL - 31

SP - 210

EP - 219

JO - Journal of Neuropsychiatry and Clinical Neurosciences

JF - Journal of Neuropsychiatry and Clinical Neurosciences

SN - 0895-0172

IS - 3

ER -